Can I read Implicit Counterfactual Data Augmentation for Robust Learning on EtoBox?

Implicit Counterfactual Data Augmentation for Robust Learning by Zhou, Xiaoling; Wu, Ou; Ng, Michael K. is a scholarly article available to read on EtoBox.

What is Implicit Counterfactual Data Augmentation for Robust Learning about?

Machine learning models are prone to capturing the spurious correlations between non-causal attributes and classes, with counterfactual data augmentation being a promising direction for breaking these spurious associations. However, generating counterfactual data explicitly poses a challenge, and incorporating augmented data into the training process decreases training efficiency. This study proposes an Implicit Counterfactual Data Augmentation (ICDA) method to remove spurious correlations and make stable predictions. Specifically, first, a novel sample-wise augmentation strategy is developed that generates semantically and counterfactually meaningful deep features with distinct augmentation strength for each sample. Second, we derive an easy-to-compute surrogate loss on the augmented feature set when the number of augmented samples becomes infinite. Third, two concrete schemes are proposed, including direct quantification and meta-learning, to derive the key parameters for the robust loss. In addition, ICDA is explained from a regularization perspective, revealing its capacity to improve intra-class compactness and augment margins at both class and sample levels. Extensive experim

Author

Zhou, Xiaoling; Wu, Ou; Ng, Michael K.

Published

2023

Language

EN